NhatHai Phan
ABSTRACT
Human behavior prediction is a key component to studying the spread of wellness and healthy behavior in a social network. In this paper, we introduce an ontology-based Restricted Boltzmann Machine (ORBM) model for human behavior prediction in health social networks. We first propose a bottom-up algorithm to learn the user representation from ontologies. Then the user representation is used to incorporate self-motivation, social influences, and environmental events together in a human behavior prediction model, which extends a well-known deep learning method, Restricted Boltzmann Machines (RBMs), so that the interactions among the behavior determinants are naturally simulated through parameters. To our best knowledge, the ORBM model is the first ontology-based deep learning approach in health informatics for human behavior prediction. Experiments conducted on both real and synthetic data from health social networks have shown the tremendous effectiveness of our approach compared with conventional methods.
- OWL Web Ontology Language. http://www.w3.org/TR/owl-ref/.Google Scholar
- The Protégé Ontology Editor and Knowledge Acquisition System. http://protege.stanford.edu/.Google Scholar
- The National Center for Biomedical Ontology. http://www.bioontology.org/.Google Scholar
- A. Bandura. Human agency in social cognitive theory. The American Psychologist, 44(9):1175--84, 1989.Google ScholarCross Ref
- N. Christakis. The hidden influence of social networks. In TED2010, 2010.Google Scholar
- N. Christakis and J. Fowler. The spread of obesity in a large social network over 32 years. The New England Journal of Medicine, 357:370--9, 2007.Google ScholarCross Ref
- D. Dou, H. Wang, and H. Liu. Semantic Data Mining: A Survey of Ontology-based Approaches. In ICSC'15, pages 244--251, 2015.Google Scholar
- R. Fichman and C. Kemerer. The illusory diffusion of innovation: An examination of assimilation gaps. Information Systems Research, 10(3):255--275, 1999. Google ScholarDigital Library
- T. Gruber. A translation approach to portable ontology specifications. Knowledge Acquisition, 5(2):199--220, 1993. Google ScholarDigital Library
- T. R. Gruber. Toward principles for the design of ontologies used for knowledge sharing? International Journal of Human-computer Studies, 43(5):907--928, 1995. Google ScholarDigital Library
- G. Hinton. Training products of experts by minimizing contrastive divergence. Neural Computation, 14(8):1771--1800, 2002. Google ScholarDigital Library
- G. Hinton, S. Osindero, and Y.-W. Teh. A fast learning algorithm for deep belief nets. Neural Computation, 18(7):1527--1554, 2006. Google ScholarDigital Library
- J. Huang, X.-Q. Cheng, H.-W. Shen, T. Zhou, and X. Jin. Exploring social influence via posterior effect of word-of-mouth recommendations. In WSDM'12, pages 573--582, 2012. Google ScholarDigital Library
- J. Kawale, A. Pal, and J. Srivastava. Churn prediction in mmorpgs: A social influence based approach. In CSE'09, pages 423--428, 2009. Google ScholarDigital Library
- D. Kil, F. Shin, B. Piniewski, J. Hahn, and K. Chan. Impacts of social health data on predicting weight loss and engagement. In O'Reilly StrataRx Conference, San Francisco, CA, October 2012.Google Scholar
- Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278--2324, 1998.Google ScholarCross Ref
- K. Lerman, S. Intagorn, J.-K. Kang, and R. Ghosh. Using proximity to predict activity in social networks. In WWW'12 Companion, pages 555--556, 2012. Google ScholarDigital Library
- X. Li, N. Du, H. Li, K. Li, J. Gao, and A. Zhang. A deep learning approach to link prediction in dynamic networks. In SDM'14, pages 289--297, 2014.Google ScholarCross Ref
- D. Lindberg, B. Humphries, and A. McCray. The Unified Medical Language System. Methods of Information in Medicine, 32(4):281--291, 1993.Google ScholarCross Ref
- B. Marcus, C. Nigg, D. Riebe, and L. Forsyth. Interactive communication strategies: implications for population-based physical activity promotion. American Journal of Preventive Medicine, 19(2):121--6, 2000.Google ScholarCross Ref
- A. Marshall, E. Eakin, E. Leslie, and N. Owen. Exploring the feasibility and acceptability of using internet technology to promote physical activity within a defined community. Health Promotion Journal of Australia, 2005(16):82--4, 2005.Google ScholarCross Ref
- M. McPherson, L. Smith-Lovin, and J. M. Cook. Birds of a feather: Homophily in social networks. Annual Review of Sociology, 27(1):415--444, 2001.Google ScholarCross Ref
- R. Pate, M. Pratt, S. Blair, and et al. Physical activity and public health. a recommendation from the centers for disease control and prevention and the american college of sports medicine. The Journal of the American Medical Association, 273(5):402--7, 1995.Google ScholarCross Ref
- K. Patrick. Information technology and the future of preventive medicine: potential, pitfalls, and policy. American Journal of Preventive Medicine, 19(2):132--5, 2000.Google ScholarCross Ref
- N. Phan, D. Dou, B. Piniewski, and D. Kil. Social restricted boltzmann machine: Human behavior prediction in health social networks. In ASONAM'15, 2015 (To appear).Google ScholarDigital Library
- N. Phan, D. Dou, X. Xiao, B. Piniewski, and D. Kil. Analysis of physical activity propagation in a health social network. In CIKM'14, pages 1329--1338, 2014. Google ScholarDigital Library
- H. Poon and P. Domingos. Sum-product networks: A new deep architecture. In IEEE ICCV Workshops, pages 689--690, 2011.Google ScholarCross Ref
- J. Prochaska, M. Zabinski, K. Calfas, J. Sallis, and K. Patrick. Pace+: interactive communication technology for behavior change in clinical settings. American Journal of Preventive Medicine, 19(2):127--31, 2000.Google ScholarCross Ref
- L. Ritterband, L. A. G.-Frederick, D. Cox, A. Clifton, R. West, and S. Borowitz. Internet interventions: in review, in use, and into the future. Professional Psychology: Research and Practice, 34:527--34, 2003.Google ScholarCross Ref
- R. M. Ryan and E. L. Deci. Intrinsic and extrinsic motivations: Classic definitions and new directions. Contemporary Educational Psychology, 25(1):54--67, 2000.Google ScholarCross Ref
- Y. Shen, R. Jin, D. Dou, N. Chowdhury, J. Sun, B. Piniewski, and D. Kil. Socialized gaussian process model for human behavior prediction in a health social network. In ICDM'12, pages 1110--1115, 2012. Google ScholarDigital Library
- P. Smolensky. Information processing in dynamical systems: Foundations of harmony theory. chapter Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1, pages 194--281. 1986. Google ScholarDigital Library
- R. Studer, V. R. Benjamins, and D. Fensel. Knowledge engineering: principles and methods. Data & knowledge engineering, 25(1):161--197, 1998. Google ScholarDigital Library
- G. Taylor, G. Hinton, and S. Roweis. Modeling human motion using binary latent variables. In NIPS'06, pages 1345--1352.Google Scholar
- The_gene_ontology_consortium. Creating the gene ontology resource: design and implementation. Genome Research, 11(8):1425--1433, August 2001.Google ScholarCross Ref
- C. Vandelanotte, K. Spathonis, E. Eakin, and N. Owen. Website-delivered physical activity interventions: A review of the literature. American Journal of Preventive Medicine, 33(1):54--64, 2007.Google ScholarCross Ref
- B. Viswanath, A. Mislove, M. Cha, and K. Gummadi. On the evolution of user interaction in facebook. In WOSN'09, pages 37--42, 2009. Google ScholarDigital Library
- M. Welling, M. Rosen-Zvi, and G. Hinton. Exponential family harmoniums with an application to information retrieval. In NIPS'04, pages 1481--1488, 2004.Google Scholar
- J. Yang, X. Wei, M. Ackerman, and L. Adamic. Activity lifespan: An analysis of user survival patterns in online knowledge sharing communities. In ICWSM'10, 2010.Google Scholar
- M. Zaslavskiy, F. Bach, and J.-P. Vert. A path following algorithm for graph matching. In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 5099, pages 329--337. 2008. Google ScholarDigital Library
- Y. Zhu, E. Zhong, S. Pan, X. Wang, M. Zhou, and Q. Yang. Predicting user activity level in social networks. In CIKM'13, pages 159--168, 2013. Google ScholarDigital Library
Index Terms
- Ontology-based deep learning for human behavior prediction in health social networks
Recommendations
A personal health recommender system incorporating personal health records, modular ontologies, and crowd-sourced data
ASONAM '16: Proceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and MiningWe present an architecture for a Personal Health Recommender System (PHRS) that begins with a person's personal electronic health record (PEHR) and augments it by combining crowd-sourced data mined for symptoms, diseases, treatments and best practices, ...
Social infobuttons: integrating open health data with social data using semantic technology
SWIM '13: Proceedings of the Fifth Workshop on Semantic Web Information ManagementThere is a large amount of free health information available for a patient to address her health concerns. HealthData.gov includes community health datasets at the national, state and community level, readily downloadable. There are also patient-...
Semantic Description of Social Network Based on Ontology
ICEE '10: Proceedings of the 2010 International Conference on E-Business and E-GovernmentTraditional social network only consider the structural characteristics of a social organization, but more information about nodes and edges cannot be exploited. The method of using ontology to describe social network is studied in this paper, which ...
Reviews
Thierry Edoh
Predictive behavior modeling is the use of mathematical and statistical techniques and/or data mining to predict future events or human behavior [1]. In [2], a set of new predictive modeling techniques is presented. These techniques can be used independently or in combination with traditional modeling techniques to predict medical outcomes, particularly in case of prostate cancer treatment. Beyond the prediction of medical outcomes, these techniques could also be considered in modeling and predicting human behavior. In [3], for example, the authors use dynamic Markov models, a mathematical method, to recognize human behavior. More interesting are the works of Ajzen and Fishbein [4-7] on human behavior prediction, using for their prediction functions different parameters such as human attitude, perceived nom, and self-efficacy. The perceived nom, which is social pressure, has two aspects-injunctive and descriptive nom-both related to how the social network importantly impacts human behavior. Nowadays, the Internet is an important platform where social activities are increasingly taking place and social communities are being built. The Internet is thus a source of information about individuals' behaviors, health information, and so on. The Internet has therefore become an appropriate source to track and analyze human behavior in online communities. The authors of this paper seem to be pioneers in using ontology-based learning for human behavior prediction. They extend the set of predictive modeling techniques for event or human behavior prediction. This paper is well written and structured; I cannot find any weakness. The authors judiciously explain their methodology, provide a well-described background tutorial, and judiciously point out the novelty of their predictive human behavior modeling technique. I recommend this paper to students and researchers working on health informatics, human behavior prediction, and predictive analytics. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments